Activity landscape image analysis using convolutional neural networks

Table 5 Classification of models trained on black and white images

Collection	RF	SVM	CNN	Metric
1	0.48 ± 0.01	0.44 ± 0.01	0.62 ± 0.02	Accuracy
	0.47 ± 0.01	0.45 ± 0.01	0.62 ± 0.02	F1
	0.21 ± 0.02	0.16 ± 0.01	0.43 ± 0.04	MCC
2	0.46 ± 0.01	0.43 ± 0.01	0.61 ± 0.03	Accuracy
	0.46 ± 0.01	0.44 ± 0.01	0.61 ± 0.03	F1
	0.20 ± 0.02	0.15 ± 0.02	0.42 ± 0.04	MCC
3	0.47 ± 0.01	0.46 ± 0.02	0.60 ± 0.02	Accuracy
	0.47 ± 0.01	0.46 ± 0.02	0.60 ± 0.02	F1
	0.20 ± 0.02	0.19 ± 0.03	0.41 ± 0.03	MCC
4	0.45 ± 0.02	0.47 ± 0.03	0.54 ± 0.05	Accuracy
	0.45 ± 0.02	0.48 ± 0.03	0.54 ± 0.04	F1
	0.17 ± 0.03	0.21 ± 0.04	0.32 ± 0.07	MCC
5	0.41 ± 0.03	0.39 ± 0.01	0.70 ± 0.05	Accuracy
	0.41 ± 0.03	0.39 ± 0.01	0.69 ± 0.04	F1
	0.12 ± 0.05	0.09 ± 0.02	0.54 ± 0.07	MCC
6	0.52 ± 0.03	0.51 ± 0.02	0.69 ± 0.07	Accuracy
	0.52 ± 0.04	0.51 ± 0.03	0.69 ± 0.07	F1
	0.29 ± 0.05	0.26 ± 0.03	0.53 ± 0.10	MCC
7	0.69 ± 0.02	0.68 ± 0.01	0.73 ± 0.02	Accuracy
	0.69 ± 0.02	0.68 ± 0.01	0.73 ± 0.02	F1
	0.53 ± 0.03	0.52 ± 0.02	0.59 ± 0.04	MCC

The table summarizes classification performance for color-coded 3D AL and Ref-AL images using RF, SVM, and CNN models trained on b/w images. All values reported are averages and standard deviations over 10 independent trials

ISSN: 1758-2946